metadata
license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_base_rms_0001_fold5
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8536585365853658
hushem_5x_deit_base_rms_0001_fold5
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.3118
- Accuracy: 0.8537
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5446 | 1.0 | 28 | 1.3850 | 0.2195 |
| 1.371 | 2.0 | 56 | 1.0037 | 0.4878 |
| 0.7358 | 3.0 | 84 | 0.5519 | 0.7561 |
| 0.2869 | 4.0 | 112 | 0.6592 | 0.7561 |
| 0.1411 | 5.0 | 140 | 0.6324 | 0.8780 |
| 0.0266 | 6.0 | 168 | 0.8126 | 0.8049 |
| 0.0011 | 7.0 | 196 | 0.7003 | 0.8537 |
| 0.0012 | 8.0 | 224 | 1.2708 | 0.8049 |
| 0.0223 | 9.0 | 252 | 0.7784 | 0.8780 |
| 0.0109 | 10.0 | 280 | 1.2289 | 0.7805 |
| 0.0002 | 11.0 | 308 | 0.9688 | 0.8537 |
| 0.03 | 12.0 | 336 | 0.8929 | 0.8537 |
| 0.0037 | 13.0 | 364 | 0.7649 | 0.8537 |
| 0.0119 | 14.0 | 392 | 0.9677 | 0.8049 |
| 0.0001 | 15.0 | 420 | 1.0107 | 0.7805 |
| 0.0001 | 16.0 | 448 | 1.0261 | 0.7805 |
| 0.0001 | 17.0 | 476 | 1.0390 | 0.7805 |
| 0.0001 | 18.0 | 504 | 1.0514 | 0.7805 |
| 0.0001 | 19.0 | 532 | 1.0626 | 0.7805 |
| 0.0 | 20.0 | 560 | 1.0741 | 0.7805 |
| 0.0 | 21.0 | 588 | 1.0847 | 0.7805 |
| 0.0 | 22.0 | 616 | 1.0958 | 0.7805 |
| 0.0 | 23.0 | 644 | 1.1069 | 0.7805 |
| 0.0 | 24.0 | 672 | 1.1169 | 0.7805 |
| 0.0 | 25.0 | 700 | 1.1262 | 0.8049 |
| 0.0 | 26.0 | 728 | 1.1359 | 0.8049 |
| 0.0 | 27.0 | 756 | 1.1455 | 0.8049 |
| 0.0 | 28.0 | 784 | 1.1554 | 0.8049 |
| 0.0 | 29.0 | 812 | 1.1647 | 0.8049 |
| 0.0 | 30.0 | 840 | 1.1746 | 0.8049 |
| 0.0 | 31.0 | 868 | 1.1846 | 0.8049 |
| 0.0 | 32.0 | 896 | 1.1951 | 0.8049 |
| 0.0 | 33.0 | 924 | 1.2053 | 0.8293 |
| 0.0 | 34.0 | 952 | 1.2145 | 0.8293 |
| 0.0 | 35.0 | 980 | 1.2243 | 0.8537 |
| 0.0 | 36.0 | 1008 | 1.2340 | 0.8537 |
| 0.0 | 37.0 | 1036 | 1.2436 | 0.8537 |
| 0.0 | 38.0 | 1064 | 1.2528 | 0.8537 |
| 0.0 | 39.0 | 1092 | 1.2615 | 0.8537 |
| 0.0 | 40.0 | 1120 | 1.2699 | 0.8537 |
| 0.0 | 41.0 | 1148 | 1.2781 | 0.8537 |
| 0.0 | 42.0 | 1176 | 1.2859 | 0.8537 |
| 0.0 | 43.0 | 1204 | 1.2920 | 0.8537 |
| 0.0 | 44.0 | 1232 | 1.2978 | 0.8537 |
| 0.0 | 45.0 | 1260 | 1.3031 | 0.8537 |
| 0.0 | 46.0 | 1288 | 1.3073 | 0.8537 |
| 0.0 | 47.0 | 1316 | 1.3103 | 0.8537 |
| 0.0 | 48.0 | 1344 | 1.3117 | 0.8537 |
| 0.0 | 49.0 | 1372 | 1.3118 | 0.8537 |
| 0.0 | 50.0 | 1400 | 1.3118 | 0.8537 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0